Search Results for author:
Found 13 papers, 13 papers with code
Low-Precision Arithmetic for Fast Gaussian Processes
Low-precision arithmetic has had a transformative effect on the training of neural networks, reducing computation, memory and energy requirements.
Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes
A broad class of stochastic volatility models are defined by systems of stochastic differential equations.
On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification
In Bayesian regression, we often use a Gaussian observation model, where we control the level of aleatoric uncertainty with a noise variance parameter.
When are Iterative Gaussian Processes Reliably Accurate?
While recent work on conjugate gradient methods and Lanczos decompositions have achieved scalable Gaussian process inference with highly accurate point predictions, in several implementations these iterative methods appear to struggle with numerical instabilities in learning kernel hyperparameters, and poor test likelihoods.
Conditioning Sparse Variational Gaussian Processes for Online Decision-making
With a principled representation of uncertainty and closed form posterior updates, Gaussian processes (GPs) are a natural choice for online decision making.
Bayesian Optimization with High-Dimensional Outputs
However, the Gaussian Process (GP) models typically used as probabilistic surrogates for multi-task Bayesian Optimization scale poorly with the number of outcomes, greatly limiting applicability.
Fast Adaptation with Linearized Neural Networks
The inductive biases of trained neural networks are difficult to understand and, consequently, to adapt to new settings.
Kernel Interpolation for Scalable Online Gaussian Processes
Gaussian processes (GPs) provide a gold standard for performance in online settings, such as sample-efficient control and black box optimization, where we need to update a posterior distribution as we acquire data in a sequential fashion.
Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling
In this paper, we show that there are mode-connecting simplicial complexes that form multi-dimensional manifolds of low loss, connecting many independently trained models.
Similarity of Neural Networks with Gradients
A suitable similarity index for comparing learnt neural networks plays an important role in understanding the behaviour of the highly-nonlinear functions, and can provide insights on further theoretical analysis and empirical studies.
Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited
Neural networks appear to have mysterious generalization properties when using parameter counting as a proxy for complexity.
Function-Space Distributions over Kernels
The resulting approach enables learning of rich representations, with support for any stationary kernel, uncertainty over the values of the kernel, and an interpretable specification of a prior directly over kernels, without requiring sophisticated initialization or manual intervention.
Subspace Inference for Bayesian Deep Learning
Bayesian inference was once a gold standard for learning with neural networks, providing accurate full predictive distributions and well calibrated uncertainty.
